2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第10页

Clique-graph matching by preserving global & local structure 保留全局和局部结构的团图匹配

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299080

Weizhi Nie, Anan Liu, Zan Gao, Yuting Su

引用次数: 60

Learning to look up: Realtime monocular gaze correction using machine learning 学习向上看:使用机器学习的实时单目凝视校正

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299098

D. Kononenko, V. Lempitsky

引用次数: 43

Fast action proposals for human action detection and search 针对人类行为检测和搜索的快速行动方案

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298735

Gang Yu, Junsong Yuan

引用次数: 214

Transferring a semantic representation for person re-identification and search 转换语义表示用于人员再识别和搜索

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299046

Zhiyuan Shi, Timothy M. Hospedales, T. Xiang

引用次数: 210

Robust video segment proposals with painless occlusion handling 具有无痛遮挡处理的鲁棒视频片段建议

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299047

Zhengyang Wu, Fuxin Li, R. Sukthankar, James M. Rehg

引用次数: 37

Sparse composite quantization 稀疏复合量化

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299085

Ting Zhang, Guo-Jun Qi, Jinhui Tang, Jingdong Wang

{"title":"Sparse composite quantization","authors":"Ting Zhang, Guo-Jun Qi, Jinhui Tang, Jingdong Wang","doi":"10.1109/CVPR.2015.7299085","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7299085","url":null,"abstract":"The quantization techniques have shown competitive performance in approximate nearest neighbor search. The state-of-the-art algorithm, composite quantization, takes advantage of the compositionabity, i.e., the vector approximation accuracy, as opposed to product quantization and Cartesian k-means. However, we have observed that the runtime cost of computing the distance table in composite quantization, which is used as a lookup table for fast distance computation, becomes nonnegligible in real applications, e.g., reordering the candidates retrieved from the inverted index when handling very large scale databases. To address this problem, we develop a novel approach, called sparse composite quantization, which constructs sparse dictionaries. The benefit is that the distance evaluation between the query and the dictionary element (a sparse vector) is accelerated using the efficient sparse vector operation, and thus the cost of distance table computation is reduced a lot. Experiment results on large scale ANN retrieval tasks (1M SIFTs and 1B SIFTs) and applications to object retrieval show that the proposed approach yields competitive performance: superior search accuracy to product quantization and Cartesian k-means with almost the same computing cost, and much faster ANN search than composite quantization with the same level of accuracy.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122533951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 78

FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences FlowWeb:通过编织一致的、逐像素的对应来联合图像集对齐

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298723

Tinghui Zhou, Yong Jae Lee, Stella X. Yu, Alexei A. Efros

{"title":"FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences","authors":"Tinghui Zhou, Yong Jae Lee, Stella X. Yu, Alexei A. Efros","doi":"10.1109/CVPR.2015.7298723","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7298723","url":null,"abstract":"Given a set of poorly aligned images of the same visual concept without any annotations, we propose an algorithm to jointly bring them into pixel-wise correspondence by estimating a FlowWeb representation of the image set. FlowWeb is a fully-connected correspondence flow graph with each node representing an image, and each edge representing the correspondence flow field between a pair of images, i.e. a vector field indicating how each pixel in one image can find a corresponding pixel in the other image. Correspondence flow is related to optical flow but allows for correspondences between visually dissimilar regions if there is evidence they correspond transitively on the graph. Our algorithm starts by initializing all edges of this complete graph with an off-the-shelf, pairwise flow method. We then iteratively update the graph to force it to be more self-consistent. Once the algorithm converges, dense, globally-consistent correspondences can be read off the graph. Our results suggest that FlowWeb improves alignment accuracy over previous pairwise as well as joint alignment methods.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125116660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 154

Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval 用于三维形状匹配和检索的深度学习形状描述符

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298732

J. Xie, Yi Fang, Fan Zhu, E. Wong

引用次数: 134

Web scale photo hash clustering on a single machine 在单个机器上进行Web规模的照片散列集群

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298596

Yunchao Gong, Marcin Pawłowski, Fei Yang, Louis Brandy, Lubomir D. Bourdev, R. Fergus

{"title":"Web scale photo hash clustering on a single machine","authors":"Yunchao Gong, Marcin Pawłowski, Fei Yang, Louis Brandy, Lubomir D. Bourdev, R. Fergus","doi":"10.1109/CVPR.2015.7298596","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7298596","url":null,"abstract":"This paper addresses the problem of clustering a very large number of photos (i.e. hundreds of millions a day) in a stream into millions of clusters. This is particularly important as the popularity of photo sharing websites, such as Facebook, Google, and Instagram. Given large number of photos available online, how to efficiently organize them is an open problem. To address this problem, we propose to cluster the binary hash codes of a large number of photos into binary cluster centers. We present a fast binary k-means algorithm that works directly on the similarity-preserving hashes of images and clusters them into binary centers on which we can build hash indexes to speedup computation. The proposed method is capable of clustering millions of photos on a single machine in a few minutes. We show that this approach is usually several magnitude faster than standard k-means and produces comparable clustering accuracy. In addition, we propose an online clustering method based on binary k-means that is capable of clustering large photo stream on a single machine, and show applications to spam detection and trending photo discovery.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125871587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 81

Active learning for structured probabilistic models with histogram approximation 基于直方图近似的结构化概率模型主动学习

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298984

Q. Sun, A. Laddha, Dhruv Batra

引用次数: 30